baharian

Thanks! I'll just update my Theano back to the new version then.

Would it break DeepSurv if `>=` is used, as follows, ```` install_requires=[ 'theano>=0.8.2', 'lasagne==0.2.dev1', 'lifelines>=0.9.2', 'tensorboard_logger==0.0.3' ] ```` instead of `==` in `setup.py` so installing DeepSurv doesn't overwrite the existing...

I believe the default value for `activation` is `lasagne.nonlinearities.rectify`: In[]: ?deepsurv.DeepSurv Init signature: deepsurv.DeepSurv(self, n_in, learning_rate, hidden_layers_sizes=None, lr_decay=0.0, momentum=0.9, L2_reg=0.0, L1_reg=0.0, activation=, dropout=None, batch_norm=False, standardize=False) Docstring: Init docstring: This class...

Any updates on this?